Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 8887
    Prev
    Next
    INDEX
    Explanations

    URLs starting with 'http'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.17
    1.1%
    1691
    +0.08
    0.5%
    553
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.17
    0.04
    1691
    +0.08
    0.04
    553
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.72
    /**
    -1.22
    ⓧ
    -1.18
    <?
    -1.13
    
    
    -1.06
    /*
    -1.01
    /***
    
    -0.88
    <?
    
    -0.84
    /*++
    -0.84
     springfox
    -0.84
    POSITIVE LOGITS
     http
    1.16
    http
    1.06
     Manufact
    1.04
     véhic
    0.94
     https
    0.92
     catég
    0.89
     délib
    0.88
     impractica
    0.88
     rafra
    0.86
    https
    0.85
    Activations Density 0.033%

    No Known Activations